EP0899659B1 - Dispositif et méthode pour simuler plusieurs noeuds sur une machine unique - Google Patents

Dispositif et méthode pour simuler plusieurs noeuds sur une machine unique Download PDF

Info

Publication number
EP0899659B1
EP0899659B1 EP98306745A EP98306745A EP0899659B1 EP 0899659 B1 EP0899659 B1 EP 0899659B1 EP 98306745 A EP98306745 A EP 98306745A EP 98306745 A EP98306745 A EP 98306745A EP 0899659 B1 EP0899659 B1 EP 0899659B1
Authority
EP
European Patent Office
Prior art keywords
user
level
kernel
domains
domain
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Expired - Lifetime
Application number
EP98306745A
Other languages
German (de)
English (en)
Other versions
EP0899659A2 (fr
EP0899659A3 (fr
Inventor
Steven K Fought
Madhusudhan Talluri
Declan J Murphy
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Sun Microsystems Inc
Original Assignee
Sun Microsystems Inc
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Sun Microsystems Inc filed Critical Sun Microsystems Inc
Publication of EP0899659A2 publication Critical patent/EP0899659A2/fr
Publication of EP0899659A3 publication Critical patent/EP0899659A3/fr
Application granted granted Critical
Publication of EP0899659B1 publication Critical patent/EP0899659B1/fr
Anticipated expiration legal-status Critical
Expired - Lifetime legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/44—Arrangements for executing specific programs
    • G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
    • G06F9/45533—Hypervisors; Virtual machine monitors
    • G06F9/45558—Hypervisor-specific management and integration aspects
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/44—Arrangements for executing specific programs
    • G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
    • G06F9/45533—Hypervisors; Virtual machine monitors
    • G06F9/45558—Hypervisor-specific management and integration aspects
    • G06F2009/45591—Monitoring or debugging support

Definitions

  • the present invention relates generally to the simulation of parallel processing systems and particularly to the simulation of multiple kernel operating systems in a cluster processing environment.
  • a current trend in the computer industry is the interconnection of a cluster of independent computing nodes connected by a high-speed communications link.
  • Each node is associated with a number of domains, where each domain represents a process having its own address space.
  • One such domain is the operating system or kernel that provides a single system image, making the cluster look like a single machine to the user, to applications, and to the network.
  • This single system image allows user and kernel applications to invoke procedures without regard to where the procedures reside within the cluster.
  • a user application running in one node can invoke an object whose method is located in another node of the cluster without requiring the user application to know the location of the invoked method.
  • Debugging the kernel in a cluster environment presents a number of challenges. Traditional debugging tools are not suitable since they require that the debugged code be stopped in order to examine data. When the debugged code is the kernel, the kernel will be stopped in order to examine kernel data. All processing in the node ceases when the kernel is stopped. In order to avoid this situation, the debugger needs to execute on a separate node. Often, this additional resource is not available.
  • kernel procedures can only execute on one node.
  • n nodes or computers will be required. Often, these additional resources are scarce and not readily available.
  • US Patent 5,805,867 describes a multiprocessor simulation apparatus capable of simulating the process of a single processor and the communication process between processors at the same time.
  • the apparatus includes a simulator preparation portion for preparing a plurality of simulators, each of which operates independently of the others, to simulate the internal process which each of the processors to be simulated conducts independently of the others, and the communication process between processors at the same time.
  • An embodiment of the invention provides an apparatus and method for simulating on a single computer multiple kernel procedures where each kernel procedure represents a node.
  • the kernel procedures are simulated as user-level procedures thereby enabling a user to debug the kernel procedures.
  • the architecture that is simulated includes clusters of computer nodes interconnected by a communications link. Each cluster includes one or more independent computer nodes. Each node is associated with a number of domains, where each domain represents a process having its own address space.
  • One such domain is the operating system or kernel that provides a single system image, making the cluster look like a single machine to the user, to applications, and to the network. This single system image allows for user or kernel applications to invoke procedures without regard to where the procedures reside within the cluster.
  • Each kernel utilizes a number of mechanisms to achieve the single cluster system image: a door mechanism is used for inter-domain communication; an object request broker (ORB) is used to process object invocations; a gateway handler is used to interface with the ORB and the user-level domains; a transport mechanism is used to facilitate communication between the different nodes; a kernel module library is used to store kernel applications; and a cluster membership monitor procedure is used to monitor the operational status of each node in a cluster.
  • ORB object request broker
  • Each node's kernel is simulated as a user-level procedure.
  • a mechanism is provided that allows a user to configure a simulation environment having a user-specified number of simulated nodes that form one cluster. If needed, multiple clusters can be simulated on the same machine.
  • a user has the ability to select the functions that are simulated and in which node.
  • FIG. 1 there is shown a computer system 100 representing one cluster of computing nodes 102.
  • a cluster is a set of computing nodes.
  • Each computing node 102 represents an independent computer that is interconnected via a communications link 104.
  • the present invention has the capability to simulate one or more clusters. For illustration purposes only, a single cluster is illustrated in Fig. 1.
  • the communications link 104 generically refers to any type of wire or wireless link between computers, such as but not limited to a local area network, a wide area network, or a combination of networks.
  • the computing nodes 102 use the communications link 104 to communicate with each other.
  • the communications link can be a System Area Network (SAN).
  • SAN System Area Network
  • Each node 102 has one or more domains 126, 128.
  • a domain 126, 128 is defined to be a process with its own address space.
  • a domain 126, 128 can have multiple threads of execution (usually called threads) that can execute user or kernel application procedures.
  • a kernel domain 128 refers to the operating system and a user domain 126 refers to a process other than the operating system.
  • the operating system or kernel 128 is the Solaris MC operating system, which is a product of Sun Microsystems, Inc. Background information on the Solaris MC operating system can be found in "Solaris MC: A Multi-Computer OS," Technical Report SMLI TR-95-48, November 1995, Sun Microsystems,
  • a user domain 126 typically executes one or more user application procedures 106.
  • a user application procedure 106 can communicate with another procedure through a door mechanism 108.
  • the user application procedure 106 can invoke objects without regard to where the object's method resides.
  • a user application procedure 106 in one domain can invoke an object where the object's method resides in a different domain either in the same node or in a different node within the cluster.
  • a door or door mechanism 108 is an interprocess communication (IPC) mechanism that enables procedures in different domains to communicate with each other.
  • the door mechanism is located in the user domain 126 and in the kernel domain 128.
  • a user application procedure 106 in one domain can issue a call through a door 108 that executes code in another domain.
  • the Solaris door mechanism is used which is described in detail in Solaris 2.6 Reference Manual, distributed by Sun Microsystems, Inc., 1997.
  • the present invention is not limited to the door mechanism.
  • Other IPC mechanisms can be used such as but not limited to sockets, Sun remote procedure calls (RPC) and System V IPC.
  • a door 108 describes a procedure in a domain 126,128 and can contain some associated state information.
  • a domain that obtains a door 108 is free to pass it along with its capabilities to another domain in the cluster.
  • a server creates a door for some service it provides and exports the door 108 to clients. Clients who obtain the door 108 may then invoke the service associated with the door 108 using the synchronous RPC semantics of a door call procedure.
  • the client procedure that issues the door call procedure migrates to the server domain associated with the door and executes the requested procedure while in the address space of the server.
  • a door return operation is performed and control migrates back to the client domain with the results, if any, from the procedure call.
  • One task of the kernel domain 128 is to facilitate communication between domains in different nodes 102.
  • a request to execute a procedure in a different node can be received by the kernel 128 from a user or kernel procedure.
  • the request is converted into a format that can be transmitted to the server node containing the requisite information needed by the server node to execute the requested procedure.
  • Various procedures in the kernel are used to establish this communication protocol without any involvement by the requesting user or kernel application procedure.
  • the various procedures used by the kernel to provide this communication are described below. A more detailed description of these procedures is found in pending patent application entitled, "A System and Method For Remote Object Invocation," serial no. 08/879,150, filed June 19, 1997, and assigned to Sun Microsystems, Inc.
  • the kernel 128 contains an ORB 114 which is used to process object invocations.
  • the ORB 114 utilizes the architecture and the specification of the Common Object Request Broker Architecture (CORBRA).
  • CORBRA Common Object Request Broker Architecture
  • a more detailed description of CORBRA can be found in The Common Object Request Broker: Architecture and Specification Object Management Group, Inc., Framingham, MA, revision 2.0, July 1995.
  • Requests to the ORB 114 can be from user-level or kernel-level application procedures.
  • the requests from the user-level application procedures 106 are transmitted to the ORB 114 through the door mechanism 108 to a gateway 112.
  • a gateway or gateway handler 112 is an extension of the door mechanism 108 that performs several tasks in order to process object invocations.
  • the object invocation is for an object's method that resides in a different node.
  • the ORB 114 transforms an object invocation request into a logical message that is sent to an appropriate node 102 through a transport procedure 116.
  • the transport procedure 116 processes messages to a node identified by a node identifier, determines a network address associated with the node identifier, and calls the network interface 118 to deliver the message.
  • the transport procedure 116 can utilize any of the well-known "transport layer" communication protocols such as but not limited to, transmission control protocol (TCP), user datagram protocol (UPD), or the like.
  • TCP transmission control protocol
  • UPD user datagram protocol
  • the ORB 114 can receive messages from another node through the transport procedure 116.
  • a kernel module library 110 includes a number of executable modules that can be dynamically loaded upon request.
  • the modules 110 perform kernel-level tasks.
  • the modules 110 include the kernel-level applications, as well as other procedures.
  • the kernel application procedures utilize the ORB 114 to process object invocations.
  • a cluster membership monitor (CMM) procedure 120 is provided to detect a node failure.
  • the CMM procedures 120 in each node communicate with each other at regular intervals to determine the operational status of the nodes in the cluster. Communication is performed at a precise time interval which is initiated by an interrupt from a software clock procedure 122.
  • the CMM procedure 120 informs the ORB 114 when a node failure occurs and when a failed node becomes operational.
  • One of the nodes 102a in each cluster is designated a root node since it contains a nameserver procedure 124.
  • the nameserver 124 is used to identify the various objects resident in the cluster.
  • the ORB 114 uses the nameserver 124 to determine the location of the object's methods.
  • Figs. 2 and 3 illustrate the simulated clusters.
  • a single computer 200 can be used to simulate one or more clusters of computing nodes.
  • the kernel of each node represents, in essence, the heart of each node.
  • Each kernel is represented as a user-level domain and is herein referred to as a simulated kernel domain 216.
  • the computer 200 has a kernel 208, one or more user domains 210, and a debugger 230.
  • the debugger 230 can be used to debug the simulated kernel domains 216 without interrupting the operation of the kernel 208.
  • the simulated clusters can be achieved using a single computer rather than multiple computers.
  • the computer 200 can be a workstation, personal computer, mainframe or any type of processing device.
  • the computer 200 includes a CPU 202, a user interface 204, and a memory 206.
  • the computer 200 has other system resources which are not shown.
  • the memory 206 of the computer 200 may be implemented as RAM (random access memory) or a combination of RAM and non-volatile memory such as magnetic disk storage.
  • the memory 206 can include the kernel domain 208, one or more user domains 210, one or more simulated kernel domains 216, a debugger procedure 230, as well as other data and procedures.
  • a user domain 210 can include a unode_load procedure 212 and a unode_create procedure 214.
  • the unode_load procedure 212 is used to execute procedures in a simulated kernel domain 216.
  • the unode_create procedure 214 is used to create one or more simulated kernel domains 216. The operation of both these procedures will be described below.
  • a simulated kernel domain 216 includes the following procedures: a control door or control door procedure 218, a transport door or transport door procedure 220, a simulated gateway or simulated gateway procedure 222, one or more shared object libraries 224, an ORB procedure 114, a CMM procedure 120, a simulated clock or simulated clock procedure 226, and a simulated transport or simulated transport procedure 228.
  • a nameserver or nameserver procedure 124 there is a nameserver or nameserver procedure 124.
  • a kernel is dependent on the inputs from the underlying hardware. As such, not all of the kernel procedures can be made to execute as a user-level procedure. Thus, some of the kernel procedures were replaced by simulated procedures and others required minor modifications to make them executable as a user-level procedure.
  • the ORB procedure 114, nameserver procedure 124, and CMM procedure 120 are basically the same procedures that reside in the kernel domain. They have been slightly modified in order to become a user-level domain by performing syntax changes and the like to certain functions internal to these procedures.
  • the kernel uses the procedure thread_create() with a certain number of arguments to create new threads. In the simulated kernel, this same function is called thr_create() and takes a different number of arguments.
  • a control door 218 is associated with each simulated kernel domain 216 and is used to facilitate communication to the user domains 210.
  • the control door 218 is linked to a simulated gateway 222 that accepts a command string specifying a particular function to execute in the simulated kernel domain 216 and its arguments.
  • the simulated gateway 222 accepts this command string and loads the requested function from the shared object library 224. It then converts the commands into arguments recognizable by the function and executes the function with the arguments.
  • the function in turn can invoke the methods of one or more objects which are processed by the ORB 114.
  • Executable modules in the simulated kernel domains 216 are represented as shared objects that are stored in a shared object library 224.
  • the shared objects represent user-level and kernel-level applications and services that are used to simulate the functioning of the kernel for debugging purposes.
  • a shared object is characterized by a module name and a function name.
  • the simulated transport procedure 228 can receive an instruction from the ORB 114 to transmit a message to another simulated kernel domain 216. This request can be to execute an object's method that resides in another simulated kernel domain 216 or to perform another task.
  • the simulated transport procedure 228 determines the transport door 220 associated with the recipient simulated kernel domain 216.
  • the simulated transport procedure 228 then performs a door call to the recipient simulated kernel domain 216. This transfers control to the intended simulated kernel domain 216 which performs the requested processing.
  • a is returned to the requesting simulated kernel domain 216 by performing a door return operation. Control is then transferred to the simulated kernel domain 216 of the requesting node which processes the response.
  • the simulated transport procedure 228 and transport door 220 can be used to transmit cluster related messages between the simulated kernel domains 216 of a cluster for other purposes.
  • communication between the CMMs of each simulated kernel domain 216 within a cluster utilizes the simulated transport procedure 228 and transport door 220. This communication is achieved through messages that are routed via the transport door 220.
  • the simulated transport procedure 228 is used to convert the messages from one format to another format recognizable to an intended recipient and to direct the message to an intended recipient.
  • a simulated clock procedure 226 is provided to replace the kernel clock 122.
  • the simulated clock procedure 226 is used to generate timely clock interrupts to the CMM procedure 120 which enables it to monitor the status of the simulated kernel domains 216 in a cluster.
  • the simulated clock procedure 226 executes as a real time thread in the Sun Solaris operating system.
  • a debugger procedure 230 is provided which can be used to debug the execution of the simulated kernel domains 216.
  • a user generates one or more nodes associated with one or more clusters (step 300). This is accomplished by calling a unode_create procedure 214 which generates a simulated kernel domain 216 representing a particular node in a particular cluster.
  • the unode_create procedure 214 takes a number of arguments such as the name of the cluster, an identifier of the node, and the number of nodes in the cluster.
  • the unode_create procedure 214 establishes a control door 218 and a transport door 220 for the simulated kernel domain and performs other initialization tasks as well.
  • Once the simulated kernel domains are created they operate in a like manner as the real system kernels and communicate with each other.
  • a user domain can execute a particular function in a simulated kernel domain (step 302). This is accomplished by executing a unode_load procedure 212 that exercises a function in a particular simulated kernel domain 216.
  • the unode_load procedure 212 can be embedded in a user application procedure.
  • the unode_load procedure 212 specifies that a particular simulated kernel domain 216 execute a particular function stored in a shared object library 224.
  • the unode_load procedure 212 is called from a user domain 210 with the following arguments: the name of the cluster, the node identifier, the name of a module in the shared object library 224, a name of a function in the module that will be executed, and the function's arguments.
  • the unode_load procedure 212 uses the cluster name and node identifier to determine the corresponding control door procedure 218.
  • the unode_load procedure 212 then invokes a door call using the control door procedure 218 which transfers control along with the arguments to the simulated gateway 222 associated with the intended simulated kernel domain 216.
  • the unode_load procedure 212 passes to the simulated gateway 222 the name of the module, the name of the function in the module, and the function's arguments.
  • the simulated gateway 222 determines the name of the shared object representing the module and dynamically loads in the corresponding shared object if it has not already been loaded into memory 206.
  • the simulated gateway 222 unpacks the arguments and converts them into a format that is recognizable by the function which is then executed.
  • the function can then execute a number of tasks which can involve communicating with other simulated kernel domains 216.
  • the ORB 114 is utilized which communicates with the other simulated kernel domains 216 through the simulated transport procedure 228 and the transport door 220.
  • a reply is returned to the unode_load procedure 212 that requested execution of the function.
  • the reply is transmitted in one format from the function to the simulated gateway 222.
  • the simulated gateway 222 then converts the reply into a format recognizable by the unode_load procedure 212 and executes a door return operation to transmit the reply to the unode_load procedure 212.
  • a debugger 230 can be used to analyze the execution of the code running in the simulated kernel domain 216 (step 304).
  • Debugging is well known in the art and the present invention is not limited to any particular type of debugging technique.
  • the debugger can execute one or more simulated kernel domains. The debugger can halt execution of a simulated kernel domain in order to analyze memory locations and data values.
  • the present invention is not limited to the computer system described in reference to Figs. 1- 3. It may be practiced without the specific details and may be implemented in various configurations, or makes or models of distributed computing systems, tightly-coupled processors or in various configurations of loosely-coupled microprocessor systems.
  • executable mediums other than a memory device such as a random access memory.
  • Other types of executable mediums can be used, such as but not limited to, a computer readable storage medium which can be any memory device, compact disc, or floppy disk.

Landscapes

  • Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Debugging And Monitoring (AREA)

Claims (13)

  1. Dispositif (200) destiné à simuler une grappe de noeuds informatiques indépendants (102), ledit dispositif comprenant :
    une pluralité de domaines (210) de niveau utilisateur, chaque domaine de niveau utilisateur ayant un espace distinct d'adresse et ayant une ou plusieurs procédures de niveau utilisateur ; et
    une pluralité de domaines (216) de noyau simulé au niveau utilisateur, chaque domaine de noyau simulé au niveau utilisateur ayant un espace distinct d'adresse et procurant une possibilité de simuler un système d'exploitation de noyau, chaque domaine de noyau simulé au niveau utilisateur incluant :
    au moins une procédure exécutable ;
    une procédure (222) de gestionnaire de passerelle destinée à recevoir une demande pour exécuter l'une, choisie, des procédures exécutables et pour exécuter la procédure exécutable choisie ; et
    un premier mécanisme (218) de communication interprocessus destiné à fournir une communication entre l'un, choisi, des domaines de noyau simulé au niveau utilisateur et les domaines de niveau utilisateur ;
    dans lequel les domaines de niveau utilisateur peuvent être mis en oeuvre pour utiliser le premier mécanisme de communication interprocessus pour demander l'exécution de l'une, particulière, des procédures exécutables dans un domaine particulier de noyau simulé au niveau utilisateur.
  2. Dispositif selon la revendication 1, dans lequel les domaines de noyau simulé au niveau utilisateur comprennent :
    une pluralité (224) de méthodes d'objet ; et
    un courtier (114) d'interrogation par objets (ORB) destiné à recevoir une demande de la procédure exécutable choisie pour appeler une méthode d'objet.
  3. Dispositif selon la revendication 1 ou la revendication 2, dans lequel un sous-ensemble des domaines de noyau simulé au niveau utilisateur représente une grappe ; et
    dans lequel les domaines de noyau simulé au niveau utilisateur comprennent une procédure (120) de surveillance d'appartenance aux communications pouvant être mise en oeuvre pour surveiller un état fonctionnel de chacun des domaines de noyau simulé au niveau utilisateur associés à une grappe particulière.
  4. Dispositif selon la revendication 3, dans lequel les domaines de noyau simulé au niveau utilisateur comprennent en outre :
    une procédure (226) d'horloge, qui peut être mise en oeuvre pour notifier la surveillance d'appartenance aux communications à un intervalle prédéfini de temps pour surveiller l'état fonctionnel de chacun des domaines de noyau simulé au niveau utilisateur associés à la grappe.
  5. Dispositif selon l'une quelconque des revendications précédentes, comprenant en outre :
    un mécanisme (230) de débogage destiné à des opérations de débogage d'un domaine de noyau simulé au niveau utilisateur ; et
    un second mécanisme (228, 220) de communication interprocessus destiné à gérer les communications entre les domaines de noyau simulé au niveau utilisateur.
  6. Procédé mis en oeuvre par ordinateur pour simuler une grappe de noeuds informatiques (102), le procédé comprenant les étapes consistant :
    à créer une pluralité de domaines (210) de niveau utilisateur, chaque domaine de niveau utilisateur incluant une ou plusieurs applications d'utilisateur ;
    à engendrer une pluralité de domaines (216) de noyau simulé au niveau utilisateur, chaque domaine de noyau simulé au niveau utilisateur représentant l'un, choisi, des noeuds informatiques, chaque domaine de noyau simulé au niveau utilisateur incluant un premier mécanisme (218) de communication interprocessus (IPC) destiné à communiquer avec les domaines de niveau utilisateur et l'un, particulier, des domaines de noyau simulé au niveau utilisateur, une pluralité de procédures exécutables et un gestionnaire (222) de passerelle destiné à exécuter une procédure exécutable ;
    à obtenir une demande provenant d'un domaine spécifique de niveau utilisateur pour exécuter une procédure exécutable dans l'un, choisi, des domaines de noyau simulé au niveau utilisateur ;
    à déterminer un premier mécanisme d'IPC associé au domaine choisi de noyau simulé au niveau utilisateur ;
    à utiliser le premier mécanisme d'IPC associé au domaine choisi de noyau simulé au niveau utilisateur pour transmettre la demande à un gestionnaire de passerelle associé au domaine choisi de noyau simulé au niveau utilisateur ; et
    à exécuter la procédure exécutable demandée dans le domaine choisi de noyau simulé au niveau utilisateur.
  7. Procédé selon la revendication 6, dans lequel ladite étape consistant à engendrer une pluralité de domaines de noyau simulé au niveau utilisateur comprend en outre l'étape consistant :
    à associer à chaque domaine de noyau simulé au niveau utilisateur un identificateur de grappe et un identificateur de noeud ; et
    dans lequel le procédé comprend en outre l'étape consistant à munir chaque domaine de noyau simulé au niveau utilisateur d'un second mécanisme (228, 220) d'IPC qui fournit un chemin de communication entre un ou plusieurs des domaines de noyau simulé au niveau utilisateur, le second mécanisme d'IPC utilisant l'identificateur de grappe et l'identificateur de noeud.
  8. Procédé selon la revendication 6 ou la revendication 7, comprenant en outre les étapes consistant :
    à associer, à une grappe particulière, un sous-ensemble des domaines de noyau simulé au niveau utilisateur ; et
    à munir chaque domaine de noyau au niveau utilisateur d'un mécanisme (120) de surveillance d'appartenance aux communications (CMM) qui surveille un état fonctionnel de chaque domaine de noyau simulé au niveau utilisateur associé à une grappe particulière à des intervalles de temps prédéfinis.
  9. Procédé selon l'une quelconque des revendications 6 à 8, dans lequel les procédures exécutables comprennent une pluralité (224) d'objets partagés référencés par un nom de module et par un nom de fonction ;
    ladite étape consistant à exécuter comprenant en outre les étapes consistant :
    à déterminer un nom de module associé à la procédure exécutable demandée ;
    à charger dynamiquement dans la mémoire le module associé au nom de module ; et
    à appeler la fonction associée à la procédure exécutable demandée.
  10. Procédé selon l'une quelconque des revendications 6 à 9, comprenant en outre les étapes consistant :
    à obtenir une réponse de la procédure exécutée ; et
    à transmettre la réponse au domaine de niveau utilisateur demandeur.
  11. Procédé selon l'une quelconque des revendications 6 à 10, comprenant en outre l'étape consistant :
    à prévoir un mécanisme (114) de courtier d'interrogation par objets (ORB) pour appeler des méthodes associées à un ou plusieurs objets référencés par la procédure exécutée demandée.
  12. Produit programme d'ordinateur comprenant des instructions exécutables par ordinateur pour mettre en oeuvre le procédé selon l'une quelconque des revendications 6 à 11.
  13. Produit programme d'ordinateur selon la revendication 12 sur un support de mémorisation lisible par ordinateur.
EP98306745A 1997-08-30 1998-08-24 Dispositif et méthode pour simuler plusieurs noeuds sur une machine unique Expired - Lifetime EP0899659B1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US08/919,128 US6074427A (en) 1997-08-30 1997-08-30 Apparatus and method for simulating multiple nodes on a single machine
US919128 1997-08-30

Publications (3)

Publication Number Publication Date
EP0899659A2 EP0899659A2 (fr) 1999-03-03
EP0899659A3 EP0899659A3 (fr) 2003-09-10
EP0899659B1 true EP0899659B1 (fr) 2007-02-21

Family

ID=25441548

Family Applications (1)

Application Number Title Priority Date Filing Date
EP98306745A Expired - Lifetime EP0899659B1 (fr) 1997-08-30 1998-08-24 Dispositif et méthode pour simuler plusieurs noeuds sur une machine unique

Country Status (5)

Country Link
US (1) US6074427A (fr)
EP (1) EP0899659B1 (fr)
JP (1) JPH11134219A (fr)
CA (1) CA2245781A1 (fr)
DE (1) DE69837130T2 (fr)

Families Citing this family (32)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6151639A (en) * 1997-06-19 2000-11-21 Sun Microsystems, Inc. System and method for remote object invocation
US6091395A (en) 1997-12-15 2000-07-18 International Business Machines Corporation Computer system and method of manipulating a graphical user interface component on a computer display through collision with a pointer
US6874123B1 (en) 1998-02-09 2005-03-29 International Business Machines Corporation Three-dimensional model to facilitate user comprehension and management of information
US6308187B1 (en) * 1998-02-09 2001-10-23 International Business Machines Corporation Computer system and method for abstracting and accessing a chronologically-arranged collection of information
US6601110B2 (en) * 1998-03-17 2003-07-29 Sun Microsystems, Inc. System and method for translating file-level operations in a non-door-based operating system to door invocations on a door server
JP2000020490A (ja) * 1998-07-01 2000-01-21 Fujitsu Ltd 遠隔手続き呼出し機構またはオブジェクトリクエストブローカ機構を有する計算機、データ転送方法、および転送方法記憶媒体
US6772107B1 (en) * 1999-11-08 2004-08-03 J.D. Edwards World Source Company System and method for simulating activity on a computer network
US7013251B1 (en) * 1999-12-15 2006-03-14 Microsoft Corporation Server recording and client playback of computer network characteristics
AU7693201A (en) * 2000-07-27 2002-02-13 Bea Systems Inc System and method for concentration and load-balancing of requests
US7596484B1 (en) 2000-11-15 2009-09-29 Itt Manufacturing Enterprises, Inc. Network node emulator and method of node emulation
US6877108B2 (en) 2001-09-25 2005-04-05 Sun Microsystems, Inc. Method and apparatus for providing error isolation in a multi-domain computer system
US7020753B2 (en) 2002-01-09 2006-03-28 Sun Microsystems, Inc. Inter-domain data transfer
US7231334B2 (en) * 2002-04-18 2007-06-12 International Business Machines Corporation Coupler interface for facilitating distributed simulation of a partitioned logic design
US7158925B2 (en) * 2002-04-18 2007-01-02 International Business Machines Corporation Facilitating simulation of a model within a distributed environment
US7437556B2 (en) * 2003-05-09 2008-10-14 Sun Microsystems, Inc. Global visibility controls for operating system partitions
US8892878B2 (en) * 2003-05-09 2014-11-18 Oracle America, Inc. Fine-grained privileges in operating system partitions
US20040226017A1 (en) * 2003-05-09 2004-11-11 Leonard Ozgur C. Mechanism for associating resource pools with operating system partitions
US7337445B1 (en) 2003-05-09 2008-02-26 Sun Microsystems, Inc. Virtual system console for virtual application environment
US7188120B1 (en) 2003-05-09 2007-03-06 Sun Microsystems, Inc. System statistics virtualization for operating systems partitions
US7461080B1 (en) 2003-05-09 2008-12-02 Sun Microsystems, Inc. System logging within operating system partitions using log device nodes that are access points to a log driver
US7389512B2 (en) * 2003-05-09 2008-06-17 Sun Microsystems, Inc. Interprocess communication within operating system partitions
US20040226015A1 (en) * 2003-05-09 2004-11-11 Leonard Ozgur C. Multi-level computing resource scheduling control for operating system partitions
US20040236562A1 (en) * 2003-05-23 2004-11-25 Beckmann Carl J. Using multiple simulation environments
US7228458B1 (en) * 2003-12-19 2007-06-05 Sun Microsystems, Inc. Storage device pre-qualification for clustered systems
US8181182B1 (en) 2004-11-16 2012-05-15 Oracle America, Inc. Resource allocation brokering in nested containers
CN100394388C (zh) * 2005-06-16 2008-06-11 武汉理工大学 单机环境中构建制造网格实验系统的方法
US7882227B2 (en) 2006-02-23 2011-02-01 Oracle America, Inc. Mechanism for implementing file access control across a network using labeled containers
US7885975B2 (en) 2006-02-23 2011-02-08 Oracle America, Inc. Mechanism for implementing file access control using labeled containers
US8938473B2 (en) 2006-02-23 2015-01-20 Oracle America, Inc. Secure windowing for labeled containers
US8938554B2 (en) 2006-03-02 2015-01-20 Oracle America, Inc. Mechanism for enabling a network address to be shared by multiple labeled containers
US8082289B2 (en) 2006-06-13 2011-12-20 Advanced Cluster Systems, Inc. Cluster computing support for application programs
CN100524221C (zh) * 2007-12-28 2009-08-05 中国科学院计算技术研究所 一种并行模拟器及方法

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH07281925A (ja) * 1994-04-06 1995-10-27 Fujitsu Ltd マルチプロセッサシミュレーション装置
US5671352A (en) * 1995-07-07 1997-09-23 Sun Microsystems, Inc. Error injection to a behavioral model
US5812780A (en) * 1996-05-24 1998-09-22 Microsoft Corporation Method, system, and product for assessing a server application performance

Also Published As

Publication number Publication date
JPH11134219A (ja) 1999-05-21
DE69837130T2 (de) 2007-11-15
DE69837130D1 (de) 2007-04-05
EP0899659A2 (fr) 1999-03-03
US6074427A (en) 2000-06-13
CA2245781A1 (fr) 1999-02-28
EP0899659A3 (fr) 2003-09-10

Similar Documents

Publication Publication Date Title
EP0899659B1 (fr) Dispositif et méthode pour simuler plusieurs noeuds sur une machine unique
US6393497B1 (en) Downloadable smart proxies for performing processing associated with a remote procedure call in a distributed system
US6487607B1 (en) Methods and apparatus for remote method invocation
EP0850446B1 (fr) Passerelle pour environnement client-serveur
US6272559B1 (en) Deferred reconstruction of objects and remote loading for event notification in a distributed system
US7383550B2 (en) Topology aware grid services scheduler architecture
Holder et al. System support for dynamic layout of distributed applications
Keller et al. Anatomy of a Resource Management System
JP2004536382A (ja) 置換可能なサービス品質機能のあるネットワーク通信チャネルコンポーネントを選択するために、置換可能なコンポーネントを用いるシステム、方法及び製造物
KR100370548B1 (ko) 임베디드 시스템의 통합 소프트웨어 개발 프레임워크를제공하는 실시간 미들웨어 장치 및 그 서비스 방법
Gu et al. JBSP: A BSP programming library in Java
Brugali et al. Service component architectures in robotics: The sca-orocos integration
EP1057113B1 (fr) Reconstitution differee d'objets et telechargement de notifications d'evenements dans un systeme decentralise
EP1058880A1 (fr) Serveurs mandataires chargeables executant des traitements associes a une procedure de teleappel
Warrender et al. Job scheduling in a high performance computing environment
Ayres et al. Stage: Python with actors
Tang et al. SNCL: a supernode OpenCL implementation for hybrid computing arrays
Schmidt et al. TAO: a High-performance ORB Endsystem Architecture for Real-time CORBA
CN117827454A (zh) 任务处理方法及装置
Schmidt Using Design Patterns and Frameworks to Develop Object-Oriented Communication Systems.
Saridogan et al. A Real-Time and Distributed System with Programming Language Abstraction.
EP1235149A2 (fr) Reconstitution différée d'objets et téléchargement de notifications d'événements dans un système décentralisé
Wang et al. Overall Introduction to JiniSolve-a Jini Based Grid Computing Framework
Chen et al. C2AS: An agent-based distributed and parallel processing virtual machine
Tsuchiya et al. Simulation of distributed processing networks

Legal Events

Date Code Title Description
PUAI Public reference made under article 153(3) epc to a published international application that has entered the european phase

Free format text: ORIGINAL CODE: 0009012

AK Designated contracting states

Kind code of ref document: A2

Designated state(s): AT BE CH CY DE DK ES FI FR GB GR IE IT LI LU MC NL PT SE

AX Request for extension of the european patent

Free format text: AL;LT;LV;MK;RO;SI

RAP1 Party data changed (applicant data changed or rights of an application transferred)

Owner name: SUN MICROSYSTEMS, INC.

PUAL Search report despatched

Free format text: ORIGINAL CODE: 0009013

AK Designated contracting states

Kind code of ref document: A3

Designated state(s): AT BE CH CY DE DK ES FI FR GB GR IE IT LI LU MC NL PT SE

AX Request for extension of the european patent

Extension state: AL LT LV MK RO SI

17P Request for examination filed

Effective date: 20040218

17Q First examination report despatched

Effective date: 20040324

AKX Designation fees paid

Designated state(s): DE FR GB

GRAP Despatch of communication of intention to grant a patent

Free format text: ORIGINAL CODE: EPIDOSNIGR1

GRAS Grant fee paid

Free format text: ORIGINAL CODE: EPIDOSNIGR3

GRAA (expected) grant

Free format text: ORIGINAL CODE: 0009210

AK Designated contracting states

Kind code of ref document: B1

Designated state(s): DE FR GB

REG Reference to a national code

Ref country code: GB

Ref legal event code: FG4D

REF Corresponds to:

Ref document number: 69837130

Country of ref document: DE

Date of ref document: 20070405

Kind code of ref document: P

EN Fr: translation not filed
PLBE No opposition filed within time limit

Free format text: ORIGINAL CODE: 0009261

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: NO OPPOSITION FILED WITHIN TIME LIMIT

26N No opposition filed

Effective date: 20071122

GBPC Gb: european patent ceased through non-payment of renewal fee

Effective date: 20070824

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: FR

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20071012

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: DE

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20080301

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: GB

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20070824

Ref country code: FR

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20070221